🕸️ Sparse Vectors - emschwartz · Scour

Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models

arxiv.org·20h

🧠LLM Inference

A History of Large Language Models

gregorygundersen.com·1d

🧠LLM Inference

Efficient Learning of Sparse Representations from Interactions

arxiv.org·1d

🕸️Sparse Embeddings

LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling

huggingface.co·9h·

Discuss: Hacker News

🔤Tokenization

Show HN: Detecting coordinated financial narratives with embeddings and AVX2

news.ycombinator.com·18h·

Discuss: Hacker News

🐯TigerBeetle

Carnegie Mellon at NeurIPS 2025

blog.ml.cmu.edu·1d

🛡️AI Safety

Your RAG System is probably image-blind, but it doesn’t have to be

thenewstack.io·5h

🔄LLM RAG Pipelines

N-Grams and Other Experiments

dotterrer.bearblog.dev·1d

📝Text Parsing

Building a semantic search engine in ±250 lines of Python

bart.degoe.de·3d·

Discuss: Hacker News

Owning the AI Pareto Frontier

latent.space·3h

(Re)Discovering Natural Laws

lesswrong.com·3h

🎯Vector Quantization

Building an Obsidian RAG with DuckDB and MotherDuck

ssp.sh·3h

Short URLs for long documents

sindark.com·5h

Longform links: solidifying your world view

abnormalreturns.com·10h

🔗Webmentions

Stewarding AI in agriculture research

science.org·11h

🔍AI Interpretability

Google unveils WAXAL, a new open speech dataset for 21 African languages to ease speech technology development; African institutions own the dataset (Damilare D...

techmeme.com·18h

Transferable enantioselectivity models from sparse data

nature.com·1d

🔬Maillard Reaction

AI Inference Needs A Mix-And-Match Memory Strategy

semiengineering.com·17h

🏗️LLM Infrastructure

🔗 Explainer: Tree-sitter vs. LSP

yellowduck.be·16h

UbiquitousLearning/mllm: Fast Multimodal LLM on Mobile Devices

github.com·16h

🏗️LLM Infrastructure

Loading more...